Open kikyo97 opened 3 years ago
Can the prior distribution be arbitrarily set? In the CNN, the weight can be optimized by the back propagate. However, in the BCNN, the W_mu and W_sigma always seem to be approximated the initial prior distribution?
Can the prior distribution be arbitrarily set? In the CNN, the weight can be optimized by the back propagate. However, in the BCNN, the W_mu and W_sigma always seem to be approximated the initial prior distribution?